AI Coding, Tools for Building AI (TBLC AI Conference)
Download as PPTX, PDF0 likes159 views
The document describes an advanced AI coding session led by Brian Pichman, focusing on hands-on experiences that blend coding theory with practical applications. Participants will explore various AI gadgets and tools while learning about the latest developments in AI technology. Key features of the training include the use of the OpenAI API, instruction on temperature, frequency, and presence penalties, and the importance of providing context in prompts.
AI Coding, Tools for Building AI (TBLC AI Conference)
- 2. Description • Embark on an engaging journey into the world of AI coding with Brian Pichman from the Evolve Project. This advanced track offers participants hands-on experiences in coding AI, blending theory with practice. Explore the latest games/gadgets/gizmos designed to educate and enhance skills in coding alongside AI. This session is perfect for those who are curious about what's it take to code AI and learn about cutting-edge developments in AI technology
- 4. AI Gadgets!
- 7. Miko
- 8. Luka
- 9. Finch
- 12. Intelino
- 14. Marty
- 15. https://userguides.robotical.io/martyv2/userguides/martyblocks/machinelearning/image
- 16. CoDrone
- 17. Zumi
- 18. Kais Education
- 21. Resources We Need • OpenAI API • Webserver • We won’t be working on webservers that need GPUs, as we will leverage an API • HuggingFace
- 23. Trained Data with Personalities 1.Temperature: 1.This controls the randomness of the model's responses. 2.Lower temperature (e.g., 0.0) means more predictable and conservative responses. 3.Higher temperature (e.g., 1.0) makes responses more creative and less predictable. 2.Frequency Penalty: 1.This reduces the model's likelihood of repeating the same line of thought or content. 2.A higher frequency penalty discourages repetition. 3.A value of 0 means no penalty for repetition. 3.Presence Penalty: 1.This affects the likelihood of introducing new concepts or topics in the response. 2.A higher presence penalty encourages the model to talk about new things. 3.A value of 0 means no emphasis on new content. Providing Context: You can include specific instructions or context in your prompt. For example, "Act like a friendly and knowledgeable assistant" sets a tone and character for the model's responses.
- 27. Lets Look At Code • ailab.libchalk.com/gameshow
Editor's Notes
- #6: XanderGlasses are wearable assistive technology for people with severe hearing challenges. Everyday situations—background noises, multiple speakers, and low-voices—impede understanding and create strain. Severity intensifies with age causing individuals to withdraw and can contribute to cognitive decline.
- #13: The intelino smart train offers both screen-free and app-connected play modes. It can help children engage in hands-on interactive play and teach them how to code. The train is intuitive and not intimidating for students and teachers alike.